Profile
Ayoub Oulad Ali
PhD student at CMAP, École Polytechnique, working on machine learning for scientific and medical imaging. Background in applied mathematics (Sorbonne Université).
Research direction
My work is about making machine learning models mathematically grounded: generative models that respect physical structure, self-supervised representations that remain interpretable, and uncertainty estimates that stay honest when data are scarce. The main application is polarimetric Mueller imaging of biological tissue.
Academic path
- PhD student, CMAP, École PolytechniqueThesis within the IMOCEP project (PEPR Maths-Vives): Mueller polarimetric imaging for preterm birth risk and cervical cancer. Supervised by Erwan Le Pennec (CMAP), co-supervised with Pierangelo (LPICM).
- Research internship, CMAP, École PolytechniquePhysics-informed generative models for Mueller matrix imaging.
- MSc, Applied Mathematics (MS2A)Sorbonne Université. Winner, ENS Data Challenge 2025.
- M1, Applied MathematicsSorbonne Université.
- BSc, Mathematics and Computer ScienceUniversité de Nîmes.
Teaching
2026–27: Introduction to Machine Learning (APM_51434_EP, Master X-HEC), Monte Carlo Methods (APM_51056_EP, Engineering Cycle). Course materials are on the teaching page.